Please consider buying my two albums Sisters of the Wicked and Danger Ahead, my book Dracula and also please check out my YouTube channel. Civitai won't support creators, so any purchase is a real help. Thanks.
DRACULA https://www.amazon.com/dp/B0FM4DXYPL
Sisters of the Wicked https://amazon.com/music/player/albums/B0DSJY3ZHY?marketplaceId=ATVPDKIKX0DER&musicTerritory=US&ref=dm_sh_CdyeuxIBNBDOjZ1hpB1PPJxT0
Danger Ahead https://www.amazon.com/music/player/albums/B0DB2DV354
Music In The Machine https://www.youtube.com/@musicinthemachine/videos
Acorn Is Boning XL V3
V3 came about after I had been away from SDXL for probably close to a year. I was working with a company trying to make realistic characters for use in online chat avatars that were NSFW. They were using Lustify. In working with it, I found it to have some good qualities, but not very good prompt adherence. I decided to go back to my original Acorn Is Boning XL as the base for a new model. V1 didn't look quite as realistic as V2, but it had better prompt adherence, so I used block merging to graft on the better visual look of Lustify onto the better composition and prompt adherence of Acorn Is Boning XL. I made a few versions for testing and found two of them to be very good and fairly similar. Here I posted version 3.0 and posted v3.1 for online generation over at Tensor.Art. https://tensor.art/models/860244001473710239/Acorn-Is-Boning-XL3-3.1
You can try it out over there if you like and compare.
Acorn Is Boning XL V2
https://www.youtube.com/@musicinthemachine/videos
I would appreciate a follow and any comments or any posted results of images. Thanks.
For V2 I was able to improve the photorealism as well as the consistency of better hands.
Like with my primary model, Acorn Is Spinning XL V4, I changed my default generation resolution to 1024 X 1328. I think this change was part of the reason for the hand improvement as I get improvement in my previous models at that resolution as well.
I get tired of all the same old porn poses so in this initial gallery, I have included a mix of regular poses along with some img2img stuff and some fantasy themed porn. If you are trying to reproduce my images and can't, it's probably one of the img2img pics. Enjoy!!
My go to sampler is still DPM++ 2M SDE Heun Exponential, typically either 30 or 60 steps with CFGs from 2 to 7, more often 2 to 3.5.
Acorn Is Boning XL
This is the first SDXL version of my Acorn Is Boning model. If you enjoy it, please follow me. I enjoy working on models and hope to keep doing it. Getting in the Creator's Program is based on followers so far so I need all I can get. It is much appreciated.
https://www.youtube.com/@musicinthemachine/videos
I use some of my models for videos on my YouTube page if you want to check it out.
As with my previous 1.5 versions, I made a randomizer prompt that takes advantage of dynamic prompts. You can set the seed to randomize and run off batches. Go back to tweak those than stand out to you. Enjoy.
highest quality photograph of beautiful naked woman {(vaginal sex:1.5) with man, erection | (from above, BLOWJOB, big cock) | (manually masturbating:1.3) with (blue glass dildo insertion:1.3) | (kneeling), (receives cum in open mouth from man's cock:1.4) | (squatting, peeing piss:1.4) | (licking penis, cum:1.4) | (giving deep throat blowjob:1.4) | (having sex with another woman:1.4), (manual dildo inserted:1.5) | (POV BLOWJOB:1.4) | (having anal sex:1.4) | (kneeling masturbation, touching own pussy:1.4)} {in the bathroom | in hot tub | in the kitchen | by the pool | in bedroom | on rooftop in the city}, {ginger | blonde | brunette} {long | medium | short} hair, {petite | skinny | chubby} body, {(large breasts:1.3) | (medium breasts:1.3) | (small breasts:1.3) | (huge breasts:1.3)}, (intricately detailed skin), (perfect lips), 18 years old, high contrast
Negative: (watermark:1.5), (anime, eye contact, misaligned:1.4), (missing limbs:1.5), (blurry), (deformed iris), (deformed legs) (extra feet, extra hands), (lipstick), (two dicks)
DPM++ 2M SDE Heun Exponential is my preferred sampler but many work just fine.
I prefer to use 40 steps or more, but you can get good results at lower steps as well, at least down to 20.
CFGs from 3 to 9 all work pretty well.
Description
Updated version of Acorn Is Boning XL. I didn't know if I would ever come back to SDXL, but I have found there are some things that SDXL does better than Flux and I get better results when I have a workflow using both SDXL and Flux, so here I am again. Feel free to test it out and see what you think.
FAQ
Comments (18)
but it can draw 'woman standing from behind' ?
It draws it just fine when I do it. I just tried about 5 variations and they all come out good.
https://civitai.com/posts/18083928
Here are a few examples.
Thanks for the updated version, can you please state what models you used in the new merge.
Cheers and keep it up
I was working with a company on a project to create AI girls people could chat with. They were having trouble getting realistic looking models for the more NSFW chats. They were using Flux for the SFW and trying Lustify for the SNFW. I worked with them for a while and I found Lustify to have some upside, but it didn't have very good prompt adherence. You could get some good images, but it was just basically a crap shoot to regenerate until until you happen to get one you like. That prompted me to get back in the SDXL game. For this new version of Boning, I went back and started with Acorn Is Boning XL V1. XL V2 had improved some things like skin texture but V1 had better prompt adherence. So I kept V1 as the base for this one. I used block merging to import the better skin textures and photo quality of Lustify onto the much superior base and prompt adherence of my original Acorn Is Boning XL. So it's mostly Acorn Is Boning XL V1 with a facelift.
@Seeker70 Thanks for answering, currently trying the model, will post good outputs.
Glad to see you're still finding good approaches in SDXL and SD1.5 - like it! Thank you very much :-)
Yeah, I moved on to Flux when it came out, and I still like Flux. I found though that it has some serious limits on trying to get different body types and faces. I had been away from SDXL for quite a while but decided to take a new look at it and found I was able to make some pretty big improvements in my original Acorn Is Boning XL model now. This one keeps a lot of the prompt adherence of Boning XL V1 but really improves the image quality.
Thanks for this! Any plans to release a FLUX version?
Probably unlikely any time soon. Unfortunately, I just don't have the kind of resources needed to train Flux. It has very strong censorship, especially with the male body. For women, there have been a huge amount of Lora models to draw from to modify it, but not very much for male, and not enough quality Loras of sex action. Since I can't train Flux, Lora merging is the only way I can create my versions of Flux. I would love to have a Flux version of Acorn Is Boning, but I am not sure when I might be able to do it.
how to get this, DPM++ 2M SDE, Heun Exponential. Heun Exponential is not in the schedulers in comfyui.
I use ForgeUI which has it. When I use Comfy I usually use DPM++2M SDE GPU Exponential which seems to be the closest I can find. I rarely use Comfy though.
Why do the faces always look bad? It's probably something I'm overlooking on my end...because I'm new to this. But even when I copy the prompts from galleries here...everything comes out looking good, except the faces. They look kind of smeared with weird triangular eyes. Again, the bodies and poses look great...it's just the faces that look awful.
It's kinda hard to say without more info. What setting are you using? Sampler, scheduler, steps, do you use Adetailer? Adetailer is usually the key to improving faces. I normally use it with a prompt of "detailed face, eyebrows, natural skin texture, slight skin blemishes, imperfect skin, skin pores, goosebumps, translucent skin, subsurface scattering, slight fine wrinkles, beauty spot, detailed eyes, light reflections in the eyes" with denoising set at about 0.6 using about 60 steps. That is, with the option set in Adetailer to use "separate steps" so that the model runs the overall image first and then Adetailer runs after on just the face with 60 steps.
@Seeker70 Sabe me dizer onde encontro o Adetailer no ForgeUI?
@sariadne050443 Vá até a aba "Extensões", depois na segunda linha abaixo, selecione "Instalar da URL", digite essa URL na caixa superior e clique em "instalar".
https://github.com/Bing-su/adetailer.git
Esta é a URL. Após a instalação, você provavelmente vai querer voltar para a aba "Instalado" e clicar no botão "Aplicar e Reiniciar a Interface".
Good model, thanks.